Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    whales are, yet subtly, worst-case loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ിക്കാ
    0.43
     kep
    0.40
    ኼ
    0.40
     wget
    0.39
    👹
    0.39
    邂
    0.38
     말이
    0.38
     assass
    0.37
     thence
    0.37
     حضرتك
    0.37
    POSITIVE LOGITS
    ज़न
    0.39
     যন্ত্রণা
    0.39
    льному
    0.37
     Certified
    0.36
     જગ્યા
    0.36
    ఱ
    0.36
    ured
    0.36
     वजन
    0.36
    ဘ
    0.36
     certified
    0.35
    Act Density 0.000%

    No Known Activations